Papers › Unleashing the Power of Meta-tuning for Few-shot Generalization Through Sparse...

Unleashing the Power of Meta-tuning for Few-shot Generalization Through Sparse Interpolated Experts

13 Mar 2024arXiv:2403.08477archive 2025-07-28

Shengzhuang Chen, Jihoon Tack, Yunqiao Yang, Yee Whye Teh, Jonathan Richard Schwarz, Ying WEI

Recent successes suggest that parameter-efficient fine-tuning of foundation models as the state-of-the-art method for transfer learning in vision, replacing the rich literature of alternatives such as meta-learning. In trying to harness the best of both worlds, meta-tuning introduces a subsequent optimization stage of foundation models but has so far only shown limited success and crucially tends to underperform on out-of-distribution (OOD) tasks. In this paper, we introduce Sparse MetA-Tuning (SMAT), a method inspired by sparse mixture-of-experts approaches and trained to isolate subsets of pre-trained parameters automatically for meta-tuning on each task. SMAT successfully overcomes OOD sensitivity and delivers on the promise of enhancing the transfer abilities of vision foundation models beyond parameter-efficient fine-tuning. We establish new state-of-the-art results on a challenging combination of Meta-Dataset augmented with additional OOD tasks in both zero-shot and gradient-based adaptation settings. In addition, we provide a thorough analysis of the superiority of learned over hand-designed sparsity patterns for sparse expert methods and the pivotal importance of the sparsity level in balancing between in-distribution and out-of-distribution generalization. Our code is publicly available.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 7 code samples harvested from 1 repository linked to this paper: 7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 7 samples from 1 repository, 7 ran (3 with no instrument failure; 4 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

szc12153/sparse_meta_tuning officialmentioned in paperpytorchSyntology: 7 samples, 7 ran (4 instrument-failed) · 0 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

7 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
3ran · our draft was wrong
1ran; the contract check could not run
2ran

Licence: 7 of the 7 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from szc12153/sparse_meta_tuning. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

szc12153/sparse_meta_tuning official repository 7 samples, 7 ran (4 instrument-failed) · 0 unverified
collapse src/taskdatasets/meta_dataset/meta_dataset/imagenet_specification.py ran · our draft was wrong no licence file found · pointer only · f22f9e770e3f12c4 · report fixture: signature nodes:set/0/? · returned set · level recorded 2026-09-24
compute_num_query src/taskdatasets/meta_dataset/meta_dataset/sampling.py ran no licence file found · pointer only · 286b18e3571ee47f · report fixture: signature images_per_class:ndarray/1/int, max_num_query:int/0/int, num_support:tuple/1/int · returned int64 · level recorded 2026-09-24
get_ancestors src/taskdatasets/meta_dataset/meta_dataset/imagenet_specification.py ran · our draft was wrong no licence file found · pointer only · 3df50298a5193115 · report fixture: signature synsets:list/1/Synset · returned set · level recorded 2026-09-24
get_node_ancestors src/taskdatasets/meta_dataset/meta_dataset/imagenet_specification.py ran · our draft was wrong no licence file found · pointer only · ad5021d14e809d40 · report fixture: signature synset:Synset/0/? · returned set · level recorded 2026-09-24
get_total_images_per_class src/taskdatasets/meta_dataset/meta_dataset/dataset_spec.py ran · honoured contract no licence file found · pointer only · 39723338c82449eb · report fixture: signature data_spec:DatasetSpecification/0/?, class_id:NoneType/0/? · returned int · level recorded 2026-09-24
sample_class_ids_uniformly src/taskdatasets/meta_dataset/meta_dataset/sampling.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 2cd79f76eda06a94 · report fixture: signature num_ways:int/0/int, rel_classes:list/1/int · returned ndarray · level recorded 2026-09-24
sample_num_ways_uniformly src/taskdatasets/meta_dataset/meta_dataset/sampling.py ran fingerprinted no licence file found · pointer only · fcf48305474e4aa6 · report fixture: signature num_classes:int/0/int, min_ways:int/0/int, max_ways:int/0/int · returned int · level recorded 2026-09-24

Tasks

Domain GeneralizationFew-Shot Image ClassificationMeta-LearningMixture-of-ExpertsOut-of-Distribution GeneralizationTransfer Learningparameter-efficient fine-tuning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Image Classification Meta-Dataset SMAT (DINO-VIT-Base-16-224) Accuracy 85.27 #1 of 22 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections